© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 25859
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    希望大家
    -0.07
    穑
    -0.07
    רא
    -0.07
    🚚
    -0.07
    linkplain
    -0.07
    荓
    -0.07
    מנו
    -0.07
     Shawn
    -0.07
     FloatingActionButton
    -0.07
     Trait
    -0.06
    POSITIVE LOGITS
    (NO
    0.08
    癖
    0.07
    敏感
    0.07
     reform
    0.07
     Ease
    0.07
    新区
    0.07
     Athe
    0.07
    ('|
    0.07
     elderly
    0.06
    收取
    0.06
    Activations Density 0.085%

    No Known Activations